PyTorch12 min read
Build specialized multimodal models with LFM3
LFM3 is our new generation of Liquid Foundation Models (LFMs), built to be the starting point for specialized intelligence. It brings text, vision, audio, omni, and decision models onto one shared backbone, all in the 2B parameter range.
By Leonie Monigatti, Jimmy T.H. Smith, Anthony Maltsev, Maxime Labonne, Brandon, Samuel Stevens, Ryan Shubert, Tianshu Yu, Sina, Tim Seyde, Rouzbeh Amin Tafreshi, Alexander Amini, Saniya Karwa, Marc Harkonen, Anna Piunova, Calder Katyal, Ishwarya Ananthabhotla, Farris Atif, Tarek Dakhran, Paul Pak, xx, Mihir Bafna, Kyle Bruce Wheeler, Aditya Tadimeti, Alfred Eng, Karthik Macherla, Khoi Nguyen, Aldo Gael Carranza, Aurelien Lac, Tyler Murray, Raahul Vignesh, Song Duong, Ramin Hasani, Mathias Lechner,Hugging Face Blog

Read the full story
Originally published by Hugging Face Blog on Oct 27, 2026.
Comments
Sign in to join the discussion.